The technical approach to converting ephemeral AI chat sessions into persistent, production-grade agents that can run on schedules or respond to events with proper error handling and state management.
2 episodes
A CTO demonstrates how to convert Claude Desktop prototypes into production-ready AI agents using Python, Pydantic, and LangGraph. The episode walks through extracting MCP tool configurations and system prompts from chat sessions, then generating deployable code that can run on schedules or respond to events—illustrating how agent development costs are approaching zero.
Jeff Haynie, serial entrepreneur and founder of Appcelerator (acquired after reaching 1M+ developers), discusses his journey from building cross-platform mobile frameworks in 2006 to launching Agentuity, a cloud platform for AI agents. He shares lessons from raising capital in Silicon Valley, navigating acquisitions, and why he believes agentic systems will require fundamentally different infrastructure than today's human-centric cloud.
Want to go deeper?
Work With Me